Unverified50% confidenceFactExact time
The evaluation metrics include raw Recall@1 (measuring direct retrieval capability) and paired token cosine similarity (measuring the consistency of latent coordinates).
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe semantic cache uses a cosine similarity threshold of 0.92 as the criterion for determining a cache hit.71% similarUnverifiedA cosine similarity threshold is reliable only if it has been measured on your own corpus with the exact model in use, and re-measured whenever either changes.71% similarUnverified从自然语言提取待办事项的NLP评估指标通常包括精确率（Precision）和召回率（Recall）68% similarUnverified相关性检测通常采用基于预训练语言模型（如BERT、Sentence-BERT）的嵌入向量余弦相似度计算68% similarUnverified可溯源生成领域的评估标准包括归因精度（attribution precision）和归因召回率（attribution recall）67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023822API
curl https://kongchang.com/api/v1/knowledge/claims/1023822MCP
get_claim(id=1023822)